{"total":120,"rows":[{"id":"2106.08903","title":"GemNet: Universal Directional Graph Neural Networks for Molecules","created":"2021-06-02","cited_by_count":343,"area":null},{"id":"2110.03336","title":"Frame Averaging for Invariant and Equivariant Network Design","created":"2021-10-07","cited_by_count":168,"area":null},{"id":"2106.06610","title":"Scalars are universal: Equivariant machine learning, structured like classical physics","created":"2021-06-11","cited_by_count":127,"area":null},{"id":"2112.09992","title":"Weisfeiler and Leman go Machine Learning: The Story so far","created":"2021-12-18","cited_by_count":122,"area":null},{"id":"2211.06489","title":"Equivariance with Learned Canonicalization Functions","created":"2022-11-11","cited_by_count":109,"area":null},{"id":"2107.13163","title":"Statistically Meaningful Approximation: a Case Study on Approximating Turing Machines with Transformers","created":"2021-07-28","cited_by_count":102,"area":null},{"id":"2102.10333","title":"Provably Strict Generalisation Benefit for Equivariant Models","created":"2021-02-20","cited_by_count":91,"area":null},{"id":"2305.05577","title":"FAENet: Frame Averaging Equivariant GNN for Materials Modeling","created":"2023-04-28","cited_by_count":73,"area":null},{"id":"2107.01959","title":"Universal Approximation of Functions on Sets","created":"2021-07-05","cited_by_count":62,"area":null},{"id":"2210.08566","title":"Theory for Equivariant Quantum Neural Networks","created":"2022-10-16","cited_by_count":62,"area":null},{"id":"2204.07697","title":"Theory of Graph Neural Networks: Representation and Learning","created":"2022-04-16","cited_by_count":61,"area":null},{"id":"2402.16077","title":"Equivariant Frames and the Impossibility of Continuous Canonicalization","created":"2024-02-25","cited_by_count":43,"area":null},{"id":"2101.05390","title":"Universal Approximation Theorems for Differentiable Geometric Deep Learning","created":"2021-01-13","cited_by_count":41,"area":null},{"id":"2205.02956","title":"Low Dimensional Invariant Embeddings for Universal Geometric Learning","created":"2022-05-05","cited_by_count":38,"area":null},{"id":"2101.03606","title":"The Gaussian Neural Process","created":"2021-01-10","cited_by_count":34,"area":null},{"id":"2106.02346","title":"Provably Strict Generalisation Benefit for Invariance in Kernel Methods","created":"2021-06-04","cited_by_count":30,"area":null},{"id":"2307.02301","title":"Sumformer: Universal Approximation for Efficient Transformers","created":"2023-07-05","cited_by_count":30,"area":null},{"id":"2303.14269","title":"The Exact Sample Complexity Gain from Invariances for Kernel Regression","created":"2023-03-24","cited_by_count":28,"area":null},{"id":"2405.18378","title":"A Canonicalization Perspective on Invariant and Equivariant Learning","created":"2024-05-28","cited_by_count":27,"area":null},{"id":"2306.02866","title":"Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance","created":"2023-06-05","cited_by_count":26,"area":null},{"id":"2406.10685","title":"Scale Equivariant Graph Metanetworks","created":"2024-06-15","cited_by_count":24,"area":null},{"id":"2203.06153","title":"Symmetry Group Equivariant Architectures for Physics","created":"2022-03-11","cited_by_count":23,"area":null},{"id":"2210.06475","title":"Equi-Tuning: Group Equivariant Fine-Tuning of Pretrained Models","created":"2022-10-13","cited_by_count":22,"area":null},{"id":"2203.07546","title":"Permutation Invariant Representations with Applications to Graph Deep Learning","created":"2022-03-14","cited_by_count":20,"area":null},{"id":"2110.06084","title":"Implicit Bias of Linear Equivariant Networks","created":"2021-10-12","cited_by_count":19,"area":null},{"id":"2112.01741","title":"Frame Averaging for Equivariant Shape Space Learning","created":"2021-12-03","cited_by_count":19,"area":null},{"id":"2303.04745","title":"A General Theory of Correct, Incorrect, and Extrinsic Equivariance","created":"2023-03-08","cited_by_count":19,"area":null},{"id":"2401.02058","title":"Neural Collapse for Cross-entropy Class-Imbalanced Learning with Unconstrained ReLU Feature Model","created":"2024-01-04","cited_by_count":19,"area":null},{"id":"2406.07598","title":"Equivariance via Minimal Frame Averaging for More Symmetries and Efficiency","created":"2024-06-11","cited_by_count":19,"area":null},{"id":"2406.03386","title":"Learning Long Range Dependencies on Graphs via Random Walks","created":"2024-06-05","cited_by_count":18,"area":null},{"id":"2201.13279","title":"UQGAN: A Unified Model for Uncertainty Quantification of Deep Classifiers trained via Conditional GANs","created":"2022-01-31","cited_by_count":16,"area":null},{"id":"2111.15341","title":"ZZ-Net: A Universal Rotation Equivariant Architecture for 2D Point Clouds","created":"2021-11-30","cited_by_count":15,"area":null},{"id":"2302.13752","title":"A Brief Survey on the Approximation Theory for Sequence Modelling","created":"2023-02-27","cited_by_count":15,"area":null},{"id":"2312.02339","title":"Expressive Sign Equivariant Networks for Spectral Geometric Learning","created":"2023-12-04","cited_by_count":15,"area":null},{"id":"2505.10994","title":"Space Group Equivariant Crystal Diffusion","created":"2025-05-16","cited_by_count":15,"area":null},{"id":"2109.13542","title":"Convergence of Deep Convolutional Neural Networks","created":"2021-09-28","cited_by_count":13,"area":null},{"id":"2209.14991","title":"Machine learning and invariant theory","created":"2022-09-29","cited_by_count":13,"area":null},{"id":"2202.02164","title":"Group invariant machine learning by fundamental domain projections","created":"2022-02-04","cited_by_count":11,"area":null},{"id":"2203.01216","title":"A Simple and Universal Rotation Equivariant Point-cloud Network","created":"2022-03-02","cited_by_count":11,"area":null},{"id":"2205.14819","title":"Universality of Group Convolutional Neural Networks Based on Ridgelet Analysis on Groups","created":"2022-05-30","cited_by_count":11,"area":null},{"id":"2305.09900","title":"Efficient Equivariant Transfer Learning from Pretrained Models","created":"2023-05-17","cited_by_count":11,"area":null},{"id":"2208.08707","title":"Deep Neural Network Approximation of Invariant Functions through Dynamical Systems","created":"2022-08-18","cited_by_count":9,"area":null},{"id":"2401.09235","title":"A Characterization Theorem for Equivariant Networks with Point-wise Activations","created":"2024-01-17","cited_by_count":9,"area":null},{"id":"2402.08010","title":"Which Frequencies do CNNs Need? Emergent Bottleneck Structure in Feature Learning","created":"2024-02-12","cited_by_count":9,"area":null},{"id":"2104.10105","title":"Neural Networks for Learning Counterfactual G-Invariances from Single Environments","created":"2021-04-20","cited_by_count":8,"area":null},{"id":"2406.12888","title":"A Space Group Symmetry Informed Network for O(3) Equivariant Crystal Tensor Prediction","created":"2024-06-03","cited_by_count":8,"area":null},{"id":"2107.02550","title":"Universal approximation and model compression for radial neural networks","created":"2021-07-06","cited_by_count":7,"area":null},{"id":"2211.14047","title":"On the Universal Approximation Property of Deep Fully Convolutional Neural Networks","created":"2022-11-25","cited_by_count":7,"area":null},{"id":"2211.14207","title":"Invariance-Aware Randomized Smoothing Certificates","created":"2022-11-25","cited_by_count":7,"area":null},{"id":"2601.21645","title":"Identifiable Equivariant Networks are Layerwise Equivariant","created":"2026-01-29","cited_by_count":7,"area":null},{"id":"2204.11231","title":"Do ReLU Networks Have An Edge When Approximating Compactly-Supported Functions?","created":"2022-04-24","cited_by_count":6,"area":null},{"id":"2207.00292","title":"Offset equivariant networks and their applications","created":"2022-07-01","cited_by_count":6,"area":null},{"id":"2307.01583","title":"Learning Lie Group Symmetry Transformations with Neural Networks","created":"2023-07-04","cited_by_count":6,"area":null},{"id":"2307.04001","title":"Polynomial Width is Sufficient for Set Representation with High-dimensional Features","created":"2023-07-08","cited_by_count":6,"area":null},{"id":"2408.05496","title":"Variational Inference Failures Under Model Symmetries: Permutation Invariant Posteriors for Bayesian Neural Networks","created":"2024-08-10","cited_by_count":6,"area":null},{"id":"2205.06203","title":"Predicting Human Psychometric Properties Using Computational Language Models","created":"2022-05-12","cited_by_count":5,"area":null},{"id":"2104.12733","title":"Invariant polynomials and machine learning","created":"2021-04-26","cited_by_count":4,"area":null},{"id":"2110.08092","title":"Equivariant and Invariant Reynolds Networks","created":"2021-10-15","cited_by_count":4,"area":null},{"id":"2205.05500","title":"Analysis of convolutional neural network image classifiers in a rotationally symmetric model","created":"2022-05-11","cited_by_count":4,"area":null},{"id":"2308.00273","title":"Neural approximation of Wasserstein distance via a universal architecture for symmetric and factorwise group invariant functions","created":"2023-08-01","cited_by_count":4,"area":null},{"id":"2412.19778","title":"Symbolic Approximations to Ricci-flat Metrics Via Extrinsic Symmetries of Calabi-Yau Hypersurfaces","created":"2024-12-27","cited_by_count":4,"area":null},{"id":"2506.02293","title":"On Universality Classes of Equivariant Networks","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2511.18417","title":"Categorical Equivariant Deep Learning: Category-Equivariant Neural Networks and Universal Approximation Theorems","created":"2025-11-23","cited_by_count":4,"area":null},{"id":"2201.13065","title":"Rigidity Preserving Image Transformations and Equivariance in Perspective","created":"2022-01-31","cited_by_count":3,"area":null},{"id":"2202.03978","title":"Segmentation by Test-Time Optimization (TTO) for CBCT-based Adaptive Radiation Therapy","created":"2022-02-08","cited_by_count":3,"area":null},{"id":"2207.03485","title":"On Non-Linear operators for Geometric Deep Learning","created":"2022-07-06","cited_by_count":3,"area":null},{"id":"2305.12585","title":"Equivariant geometric convolutions for emulation of dynamical systems","created":"2023-05-21","cited_by_count":3,"area":null},{"id":"2305.16910","title":"Universal approximation with complex-valued deep narrow neural networks","created":"2023-05-26","cited_by_count":3,"area":null},{"id":"2309.16646","title":"Improving Equivariance in State-of-the-Art Supervised Depth and Normal Predictors","created":"2023-09-28","cited_by_count":3,"area":null},{"id":"2406.01552","title":"Tensor learning with orthogonal, Lorentz, and symplectic symmetries","created":"2024-06-03","cited_by_count":3,"area":null},{"id":"2410.05446","title":"Stability of sorting based embeddings","created":"2024-10-07","cited_by_count":3,"area":null},{"id":"2501.18116","title":"DeepFRC: An End-to-End Deep Learning Model for Functional Registration and Classification","created":"2025-01-30","cited_by_count":3,"area":null},{"id":"2502.11467","title":"Approximation of Permutation Invariant Polynomials by Transformers: Efficient Construction in Column-Size","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2509.20615","title":"Latent Twins","created":"2025-09-24","cited_by_count":3,"area":null},{"id":"2605.23156","title":"Any-Dimensional Invariant Universality","created":"2026-05-22","cited_by_count":3,"area":null},{"id":"2106.05233","title":"Analysis of convolutional neural network image classifiers in a hierarchical max-pooling model with additional local pooling","created":"2021-05-31","cited_by_count":2,"area":null},{"id":"2110.07472","title":"Capacity of Group-invariant Linear Readouts from Equivariant Representations: How Many Objects can be Linearly Classified Under All Possible Views?","created":"2021-10-14","cited_by_count":2,"area":null},{"id":"2301.03019","title":"Equivariant and Steerable Neural Networks: A review with special emphasis on the symmetric group","created":"2023-01-08","cited_by_count":2,"area":null},{"id":"2303.12856","title":"Anti-symmetric Barron functions and their approximation with sums of determinants","created":"2023-03-22","cited_by_count":2,"area":null},{"id":"2312.02146","title":"Learning Polynomial Problems with $SL(2,\\mathbb{R})$ Equivariance","created":"2023-12-04","cited_by_count":2,"area":null},{"id":"2402.15984","title":"A unified Fourier slice method to derive ridgelet transform for a variety of depth-2 neural networks","created":"2024-02-25","cited_by_count":2,"area":null},{"id":"2405.19995","title":"Symmetries in Overparametrized Neural Networks: A Mean-Field View","created":"2024-05-30","cited_by_count":2,"area":null},{"id":"2406.08966","title":"Separation Power of Equivariant Neural Networks","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2410.02176","title":"Towards Better Generalization: Weight Decay Induces Low-rank Bias for Neural Networks","created":"2024-10-03","cited_by_count":2,"area":null},{"id":"2506.09625","title":"GLGENN: A Novel Parameter-Light Equivariant Neural Networks Architecture Based on Clifford Geometric Algebras","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2506.23551","title":"A unified framework for establishing the universal approximation of transformer-type architectures","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2605.08262","title":"SLayerGen: a Crystal Generative Model for all Space and Layer Groups","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2107.09301","title":"A Bayesian Approach to Invariant Deep Neural Networks","created":"2021-07-20","cited_by_count":1,"area":null},{"id":"2206.01178","title":"Discretization Invariant Networks for Learning Maps between Neural Fields","created":"2022-06-02","cited_by_count":1,"area":null},{"id":"2208.13305","title":"Neural Network Approximation of Continuous Functions in High Dimensions with Applications to Inverse Problems","created":"2022-08-28","cited_by_count":1,"area":null},{"id":"2210.09444","title":"A tradeoff between universality of equivariant models and learnability of symmetries","created":"2022-10-17","cited_by_count":1,"area":null},{"id":"2310.09675","title":"Efficient Model-Agnostic Multi-Group Equivariant Networks","created":"2023-10-14","cited_by_count":1,"area":null},{"id":"2402.15413","title":"G-RepsNet: A Fast and General Construction of Equivariant Networks for Arbitrary Matrix Groups","created":"2024-02-23","cited_by_count":1,"area":null},{"id":"2509.23474","title":"Statistical Learning Guarantees for Group-Invariant Barron Functions","created":"2025-09-27","cited_by_count":1,"area":null},{"id":"2510.21691","title":"On Uncertainty Calibration for Equivariant Functions","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2602.20370","title":"Quantitative Approximation Rates for Group Equivariant Learning","created":"2026-02-23","cited_by_count":1,"area":null},{"id":"2109.02358","title":"Pointspectrum: Equivariance Meets Laplacian Filtering for Graph Representation Learning","created":"2021-09-06","cited_by_count":0,"area":null},{"id":"2201.09132","title":"CNN-based regularisation for CT image reconstructions","created":"2022-01-22","cited_by_count":0,"area":null},{"id":"2205.00630","title":"Design equivariant neural networks for 3D point cloud","created":"2022-05-02","cited_by_count":0,"area":null},{"id":"2205.12250","title":"Efficient anti-symmetrization of a neural network layer by taming the sign problem","created":"2022-05-24","cited_by_count":0,"area":null}],"next_cursor":"100"}